© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74532
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milky
    -0.60
    autoconfigure
    -0.60
     Entrée
    -0.59
    IsContent
    -0.58
    BagLayout
    -0.57
     continúas
    -0.57
     getIntent
    -0.57
     Promotes
    -0.57
    lious
    -0.57
    ContentAsync
    -0.57
    POSITIVE LOGITS
    PyTuple
    0.46
     disambiguazione
    0.44
    dieu
    0.41
    Televis
    0.40
     Wiktionnaire
    0.39
     religieuses
    0.39
    abestanden
    0.38
    WriteAttribute
    0.38
    Hrsg
    0.38
    érieures
    0.38
    Activations Density 0.000%

    No Known Activations